Related papers: B-AVIBench: Towards Evaluating the Robustness of L…

As Large Vision-Language Models (LVLMs) are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically…

Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively integrating the rich…

Multi-modal Large Language Models (MLLMs) have recently achieved enhanced performance across various vision-language tasks including visual grounding capabilities. However, the adversarial robustness of visual grounding remains unexplored…

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

The rapid advancement of Large Vision-Language Models (LVLMs) has enhanced capabilities offering potential applications from content creation to productivity enhancement. Despite their innovative potential, LVLMs exhibit vulnerabilities,…

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern…

Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often…

Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

The rapid advancement of Multimodal Large Language Models (MLLMs) has introduced complex security challenges, particularly at the intersection of textual and visual safety. While existing schemes have explored the security vulnerabilities…

Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do…

Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models (Omni-LLMs), which are capable of processing multi-modal information including vision and audio,…

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…

The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs…

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Understanding the vulnerabilities of Large Vision Language Models (LVLMs) to jailbreak attacks is essential for their responsible real-world deployment. Most previous work requires access to model gradients, or is based on human knowledge…

Recent advancements in Large Vision-Language Models (VLMs), have greatly enhanced their capability to jointly process text and images. However, despite extensive benchmarks evaluating visual comprehension (e.g., diagrams, color schemes, OCR…

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…